Schemas stage - Schema Manager

Schema Name: sfdl_stage_drivethru.websites_events_demo

created: 2024-12-13 03:00:10
disabled: False
format: raw
id: 2234
is_partitioned: True
is_schema_datatyped: True

name:

{
    "database": "sfdl_stage_drivethru",
    "table": "websites_events_demo"
}

type: drivethrujson

Schema Versions: 2

Version 789800

created: 2024-12-22 08:00:33

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_drivethru`",
    "DROP TABLE IF EXISTS `sfdl_stage_drivethru.websites_events_demo`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_drivethru.websites_events_demo`\n(\n`name`STRING,`eventLocation`STRING,`widgetName`STRING,`facilityId`STRING,`siteId`STRING,`pageVersion`STRING,`bucket`STRING,`data_track_click`STRING,`companyId`STRING,`event`STRING,`unitsShown`STRING,`userLong`STRING,`userLat`STRING,`widgetId`STRING,`sessionId`STRING,`categoryUsed`STRING,`timeStamp`STRING,`pageId`STRING,`type`STRING,`rg`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo'\n",
    "MSCK REPAIR TABLE sfdl_stage_drivethru.websites_events_demo"
]

hive_path: s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo
id: 789800
processed: 1

raw_data:

{
    "categoryUsed": "Vehicle",
    "companyId": "5ac68ae4-0ac1-418a-af7b-98bc192406f3",
    "data-track-click": "reserve",
    "event": "contentView",
    "eventLocation": "themeOne",
    "facilityId": "e1af3904-7595-483a-aebe-98dc7a7e9dca",
    "name": "Home Page 1",
    "pageId": "6656a9c01d267d063d4b5e75",
    "pageVersion": "c131df36-5237-415e-8ffe-541926e02067",
    "sessionId": "Awp7kUhx0ZYeMsTJpYjGnquMIvK7sNZ2",
    "siteId": "64b56c713c159605b5ac5178",
    "timeStamp": "2024-12-22T11:54:56.951Z",
    "type": "voyager/pages/types/HOME_PAGE",
    "unitsShown": 1,
    "userLat": 39.0572,
    "userLong": -94.5933,
    "widgetId": "850b43a8-06f2-46fb-a84b-b1a04a1a1303",
    "widgetName": "Text Header"
}

schema_attributes:

{
    "bucket": "string",
    "categoryUsed": "string",
    "companyId": "string",
    "data_track_click": "string",
    "event": "string",
    "eventLocation": "string",
    "facilityId": "string",
    "name": "string",
    "pageId": "string",
    "pageVersion": "string",
    "rg": "string",
    "sessionId": "string",
    "siteId": "string",
    "timeStamp": "string",
    "type": "string",
    "unitsShown": "string",
    "userLat": "string",
    "userLong": "string",
    "widgetId": "string",
    "widgetName": "string"
}

schema_name_id: 2234
schema_scan_id: 6172742
updated: 2024-12-22 08:00:47

Version 785730

created: 2024-12-13 03:00:11

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_stage_drivethru`",
    "DROP TABLE IF EXISTS `sfdl_stage_drivethru.websites_events_demo`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_drivethru.websites_events_demo`\n(\n`event`STRING,`name`STRING,`type`STRING,`pageId`STRING,`pageVersion`STRING,`userLat`STRING,`userLong`STRING,`timeStamp`STRING,`companyId`STRING,`siteId`STRING,`sessionId`STRING,`rg`STRING,`bucket`STRING,`widgetName`STRING,`widgetId`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo'\n",
    "MSCK REPAIR TABLE sfdl_stage_drivethru.websites_events_demo"
]

hive_path: s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo
id: 785730
processed: 1

raw_data:

{
    "bucket": "voyager-data-events-staging",
    "companyId": "7b40898a-c95a-4756-88ee-4729a1275427",
    "event": "pageView",
    "name": "Home Page",
    "pageId": "5aa828cb5d4f76061ab1e215",
    "pageVersion": "31c3bc3f-ad06-4674-9b50-0c1399a146cd",
    "rg": "us-east-1",
    "sessionId": "jk60DWlDqWtcsqVZUh7Ax3kR08Vy5PAR",
    "siteId": "5aa828bc7a4768a6789e2340",
    "timeStamp": "2024-12-12T21:40:26.991Z",
    "type": "voyager/pages/types/HOME_PAGE",
    "userLat": 39.0572,
    "userLong": -94.5933,
    "widgetId": "80b7ecbe-b01b-11ea-b3de-0242ac130004",
    "widgetName": "Breadcrumbs"
}

schema_attributes:

{
    "bucket": "string",
    "companyId": "string",
    "event": "string",
    "name": "string",
    "pageId": "string",
    "pageVersion": "string",
    "rg": "string",
    "sessionId": "string",
    "siteId": "string",
    "timeStamp": "string",
    "type": "string",
    "userLat": "string",
    "userLong": "string",
    "widgetId": "string",
    "widgetName": "string"
}

schema_name_id: 2234
schema_scan_id: 6157960
updated: 2024-12-13 03:00:22

Schema Scans: 2

Last at 2024-12-22 08:00:32

Scan 6172742

duration: 0:00:17.344343

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 2,
    "partitions_applied": false,
    "success": true
}

id: 6172742

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-22",
        "name": "dt",
        "type": "string",
        "value": "2024-12-22"
    },
    "s3": {
        "bucket": "sfdl-drivethrujson-drivethru-stage",
        "hive_path": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo",
        "key": "raw_incremental/websites_events_demo/dt=2024-12-22/events_06_00.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_drivethru.websites_events_demo",
        "type": "drivethrujson"
    },
    "trace_context": {
        "parent_id": 6401309643361618164,
        "service_name": "drive-thru",
        "span_id": 1293245918857890257,
        "trace_id": 7398357061518173203
    }
}

running: False
schema_name_id: 2234
start_time: 2024-12-22 08:00:32
success: True
trace_id: 7398357061518173203

Scan 6157960

duration: 0:00:14.555034

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 1,
    "partitions_applied": false,
    "success": true
}

id: 6157960

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-13",
        "name": "dt",
        "type": "string",
        "value": "2024-12-13"
    },
    "s3": {
        "bucket": "sfdl-drivethrujson-drivethru-stage",
        "hive_path": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo",
        "key": "raw_incremental/websites_events_demo/dt=2024-12-13/events_15_45.json.gz"
    },
    "schema": {
        "name": "sfdl_stage_drivethru.websites_events_demo",
        "type": "drivethrujson"
    },
    "trace_context": {
        "parent_id": 16156322823429402712,
        "service_name": "drive-thru",
        "span_id": 3225617928607482791,
        "trace_id": 2876250611021556049
    }
}

running: False
schema_name_id: 2234
start_time: 2024-12-13 03:00:10
success: True
trace_id: 2876250611021556049

Partitions:

count: 2

ddl:

[
    "ALTER TABLE\n    `sfdl_stage_drivethru.websites_events_demo`\nADD\n\n\n PARTITION (dt='2024-12-13') location 's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-13/'\n PARTITION (dt='2024-12-22') location 's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-22'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 586472,
            "location": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-13/",
            "name": "dt",
            "value": "2024-12-13"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-12-13 03:00:11",
                "last_data": "2024-12-13 03:00:11"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 588421,
            "location": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-22",
            "name": "dt",
            "value": "2024-12-22"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2024-12-22 08:00:33",
                "last_data": "2024-12-22 12:00:10"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "bucket": "string",
    "categoryUsed": "string",
    "companyId": "string",
    "data_track_click": "string",
    "event": "string",
    "eventLocation": "string",
    "facilityId": "string",
    "name": "string",
    "pageId": "string",
    "pageVersion": "string",
    "rg": "string",
    "sessionId": "string",
    "siteId": "string",
    "timeStamp": "string",
    "type": "string",
    "unitsShown": "string",
    "userLat": "string",
    "userLong": "string",
    "widgetId": "string",
    "widgetName": "string"
}

created: 2024-12-22 08:00:33

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_drivethru`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_drivethru.websites_events_demo`\n(\n`name`STRING,`eventLocation`STRING,`widgetName`STRING,`facilityId`STRING,`siteId`STRING,`pageVersion`STRING,`bucket`STRING,`data_track_click`STRING,`companyId`STRING,`event`STRING,`unitsShown`STRING,`userLong`STRING,`userLat`STRING,`widgetId`STRING,`sessionId`STRING,`categoryUsed`STRING,`timeStamp`STRING,`pageId`STRING,`type`STRING,`rg`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_drivethru.websites_events_demo`",
    "repair_table": "MSCK REPAIR TABLE sfdl_stage_drivethru.websites_events_demo"
}

Server:

hostname: schemamanager-5c55c886bf-h2ts4
name: schema_manager
process_start: 2025-10-21 13:03:27
sf_env: stage
version: 2112174301

Raw:

{
    "name": {
        "created": "2024-12-13 03:00:10",
        "disabled": false,
        "format": "raw",
        "id": 2234,
        "is_partitioned": true,
        "is_schema_datatyped": true,
        "name": {
            "database": "sfdl_stage_drivethru",
            "table": "websites_events_demo"
        },
        "type": "drivethrujson"
    },
    "partition": {
        "count": 2,
        "ddl": [
            "ALTER TABLE\n    `sfdl_stage_drivethru.websites_events_demo`\nADD\n\n\n PARTITION (dt='2024-12-13') location 's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-13/'\n PARTITION (dt='2024-12-22') location 's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-22'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 586472,
                    "location": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-13/",
                    "name": "dt",
                    "value": "2024-12-13"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-12-13 03:00:11",
                        "last_data": "2024-12-13 03:00:11"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 588421,
                    "location": "s3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo/dt=2024-12-22",
                    "name": "dt",
                    "value": "2024-12-22"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2024-12-22 08:00:33",
                        "last_data": "2024-12-22 12:00:10"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "bucket": "string",
            "categoryUsed": "string",
            "companyId": "string",
            "data_track_click": "string",
            "event": "string",
            "eventLocation": "string",
            "facilityId": "string",
            "name": "string",
            "pageId": "string",
            "pageVersion": "string",
            "rg": "string",
            "sessionId": "string",
            "siteId": "string",
            "timeStamp": "string",
            "type": "string",
            "unitsShown": "string",
            "userLat": "string",
            "userLong": "string",
            "widgetId": "string",
            "widgetName": "string"
        },
        "created": "2024-12-22 08:00:33",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_stage_drivethru`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_stage_drivethru.websites_events_demo`\n(\n`name`STRING,`eventLocation`STRING,`widgetName`STRING,`facilityId`STRING,`siteId`STRING,`pageVersion`STRING,`bucket`STRING,`data_track_click`STRING,`companyId`STRING,`event`STRING,`unitsShown`STRING,`userLong`STRING,`userLat`STRING,`widgetId`STRING,`sessionId`STRING,`categoryUsed`STRING,`timeStamp`STRING,`pageId`STRING,`type`STRING,`rg`STRING\n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-drivethrujson-drivethru-stage/raw_incremental/websites_events_demo'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_stage_drivethru.websites_events_demo`",
            "repair_table": "MSCK REPAIR TABLE sfdl_stage_drivethru.websites_events_demo"
        }
    },
    "server": {
        "hostname": "schemamanager-5c55c886bf-h2ts4",
        "name": "schema_manager",
        "process_start": "2025-10-21 13:03:27",
        "sf_env": "stage",
        "version": "2112174301"
    }
}

Schema Info